© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198148
    Prev
    Next
    INDEX
    Explanations

    win prize

    np_acts-logits-general · gemini-2.5-flash-lite

    technical and domain-specific language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     believe
    0.50
     הו
    0.46
    v
    0.46
    if
    0.46
    www
    0.46
    </code>
    0.45
    hari
    0.45
     imm
    0.43
     eastern
    0.43
     chairman
    0.43
    POSITIVE LOGITS
    丆
    0.54
     ভোগ্য
    0.51
     Función
    0.50
    侖
    0.50
    avacanam
    0.50
    
    0.49
     명령어
    0.49
    Ꮑ
    0.49
    靗
    0.48
     入っ
    0.48
    Activations Density 0.000%

    No Known Activations